oassis — web scraping, crawling and browser control for AI agents
REMOTE · API.OASSIS.DEV · SCANNED OCT 1
Scrape to markdown, map and crawl sites, drive a real browser. Pay per call, no API key, no signup.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security46
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not fully verified: no authorisation is required to call this server, and 11 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. See how to fix → View diagnostics → Unverified
- HTTPS check failed: the endpoint is reachable over plaintext HTTP. See how to fix → View diagnostics → Fail
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability66
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 2082 tokens (~189/item across 11 items; 11 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management7
- Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage94
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 83% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
- Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
How do I install the oassis — web scraping, crawling and browser control for AI… MCP server?
oassis — web scraping, crawling and browser control for AI… is a hosted endpoint at https://api.oassis.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · api.oassis.dev
claude mcp add --transport http dev-oassis-scraper-crawler 'https://api.oassis.dev/mcp'
{
"mcpServers": {
"dev-oassis-scraper-crawler": {
"url": "https://api.oassis.dev/mcp"
}
}
} {
"servers": {
"dev-oassis-scraper-crawler": {
"type": "http",
"url": "https://api.oassis.dev/mcp"
}
}
} [mcp_servers.dev-oassis-scraper-crawler] url = "https://api.oassis.dev/mcp"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"dev-oassis-scraper-crawler": {
"type": "remote",
"url": "https://api.oassis.dev/mcp",
"enabled": true
}
}
} openclaw mcp add dev-oassis-scraper-crawler --url 'https://api.oassis.dev/mcp' --transport streamable-http
mcp_servers:
dev-oassis-scraper-crawler:
url: "https://api.oassis.dev/mcp" {
"McpServers": {
"dev-oassis-scraper-crawler": {
"Transport": "http",
"Url": "https://api.oassis.dev/mcp"
}
}
} assistant mcp add dev-oassis-scraper-crawler -t streamable-http -u 'https://api.oassis.dev/mcp'
{
"mcpServers": {
"dev-oassis-scraper-crawler": {
"type": "http",
"url": "https://api.oassis.dev/mcp"
}
}
} The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 30 Sept 26 +1
- Stability: unverified → 0.03 ▲ functional
- Server version: 1.0.0 → 1.0.1 functional
- 29 Sept 26 56
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 1 Oct 2026 · Probed https://api.oassis.dev/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=oassis.dev | CN=WE1,O=Google Trust Services,C=US | 27 Sept 2026 | 26 Dec 2026 | ECDSA 256 | ECDSA-SHA256 | f753ff58f7510c290e28cb13eeceee31 |
| SANs: oassis.dev, api.oassis.dev, *.api.oassis.dev | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of api.oassis.dev. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| dev. | present | 60074 | 8 | Verified |
| oassis.dev. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://api.oassis.dev/mcp | Verified | 200 | |
| http (plaintext) | http://api.oassis.dev/mcp | Served over HTTP | 200 |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
web_act ~260
Runs actions against an open session and returns the resulting state. Actions: {navigate}, {click:{ref}}, {type:{ref,text,clear}}, {select:{ref,value}}, {press}, {scroll}, {wait}, {back}. The `ref` is the one `controls` gave you. It stops at the first failure and tells you where. $0.0005 per action.
| Name | Type | Req | Description |
|---|---|---|---|
| actions | array | yes | Actions, in order. |
| formats | array | – | Outputs you want in the same response. `controls` is the map of what can be clicked; `elements` needs `selectors`; `json` needs `json.prompt`. |
| json | object | – | For the `json` format: `prompt` and/or `schema`. |
| maxAge | number | – | Accept an answer up to this many milliseconds old. A cache hit costs $0.0002 instead of the format price. Leave it out to force a fresh render. |
| selectors | array | – | CSS selectors for `elements`. |
| sessionId | string | yes | The one web_session_open returned. |
| url | string | – | Page to process. |
| wait | object | – | When to consider the page loaded: `until`, `selector`, `timeout`. |
No output schema declared.
No examples provided.
web_batch_status ~86
Checks a batch of scrapes: status, how many are done, and the results. Free. Pass `cancel: true` to stop it and get the urls it never read refunded.
| Name | Type | Req | Description |
|---|---|---|---|
| cancel | boolean | – | Stop the batch and refund what it did not read. |
| jobId | string | yes | – |
| limit | number | – | Results to return (default 50). |
No output schema declared.
No examples provided.
web_crawl ~225
Follows a site's links and reads every page. Returns a jobId; poll it with web_crawl_status. Charged up front for the pages it is allowed to read (`limit`), and the pages it never reads are refunded. Use web_map first if you only need the urls.
| Name | Type | Req | Description |
|---|---|---|---|
| excludePaths | array | – | – |
| formats | array | – | Outputs you want in the same response. `controls` is the map of what can be clicked; `elements` needs `selectors`; `json` needs `json.prompt`. |
| includePaths | array | – | – |
| includeSubdomains | boolean | – | – |
| limit | number | – | Pages it may read (default 25, max 200). |
| maxAge | number | – | Accept an answer up to this many milliseconds old. A cache hit costs $0.0002 instead of the format price. Leave it out to force a fresh render. |
| maxDepth | number | – | How far to follow links (default 2, max 5). |
| url | string | yes | Where to start. |
No output schema declared.
No examples provided.
web_crawl_status ~86
Checks a crawl: status, pages read, discovered and still queued, and the pages themselves. Free. Pass `cancel: true` to stop it and get the unread pages refunded.
| Name | Type | Req | Description |
|---|---|---|---|
| cancel | boolean | – | Stop the crawl and refund what it did not read. |
| jobId | string | yes | – |
| limit | number | – | Pages to return (default 50). |
No output schema declared.
No examples provided.
web_feedback ~151
Tell us an answer was good or bad. FREE. Use it when a result is wrong — empty markdown, a control map missing a button, data that does not match the page — with the url or the jobId so it can be reproduced. It is the only way we learn that we read a page badly: our logs cannot tell that apart from a page that is simply like that.
| Name | Type | Req | Description |
|---|---|---|---|
| comment | string | – | What you expected and what you got. |
| reference | string | – | The jobId or sessionId it happened on. |
| route | string | – | Which tool or endpoint it is about. |
| url | string | – | The page that came out wrong. |
| verdict | string | yes | – |
No output schema declared.
No examples provided.
web_map ~159
Every url of a site, fast and cheap: its sitemap plus, optionally, the links on the page. Use it BEFORE crawling, to see what is there and decide what is worth reading. $0.0003 with `includePage: false` (no browser at all), $0.0015 with the page.
| Name | Type | Req | Description |
|---|---|---|---|
| excludePaths | array | – | – |
| includePage | boolean | – | Render the page too (default true). |
| includePaths | array | – | – |
| includeSubdomains | boolean | – | – |
| limit | number | – | Urls to return (default 1000, max 5000). |
| search | string | – | Keep only urls containing this text. |
| url | string | yes | The site to map. |
No output schema declared.
No examples provided.
web_scrape ~264
Processes a page and returns every output you ask for at once: markdown, html, links, screenshot, PDF, accessibility tree, elements by selector, AI-structured data, and `controls` (what can be clicked). One call, and a partial failure does not void the rest. From $0.001 per output. A url pointing at a PDF, Word, Excel or CSV file is converted to markdown instead, with no browser, for $0.002.
| Name | Type | Req | Description |
|---|---|---|---|
| formats | array | – | Outputs you want in the same response. `controls` is the map of what can be clicked; `elements` needs `selectors`; `json` needs `json.prompt`. |
| html | string | – | Raw HTML instead of `url`. |
| json | object | – | For the `json` format: `prompt` and/or `schema`. |
| maxAge | number | – | Accept an answer up to this many milliseconds old. A cache hit costs $0.0002 instead of the format price. Leave it out to force a fresh render. |
| selectors | array | – | CSS selectors for `elements`. |
| url | string | – | Page to process. |
| wait | object | – | When to consider the page loaded: `until`, `selector`, `timeout`. |
No output schema declared.
No examples provided.
web_scrape_batch ~244
A batch OF SCRAPES: reads a list of urls YOU give it (2 to 50, from any sites) and returns a jobId. It discovers nothing on its own — for that use web_crawl. Charged up front per url; urls that fail and urls served from the cache are refunded. Poll it with web_batch_status.
| Name | Type | Req | Description |
|---|---|---|---|
| formats | array | – | Outputs you want in the same response. `controls` is the map of what can be clicked; `elements` needs `selectors`; `json` needs `json.prompt`. |
| json | object | – | For the `json` format: `prompt` and/or `schema`. |
| maxAge | number | – | Accept an answer up to this many milliseconds old. A cache hit costs $0.0002 instead of the format price. Leave it out to force a fresh render. |
| selectors | array | – | CSS selectors for `elements`. |
| urls | array | yes | The urls to read, 2 to 50. They do not have to share a site. |
| wait | object | – | When to consider the page loaded: `until`, `selector`, `timeout`. |
No output schema declared.
No examples provided.
web_search_exa ~172
Search the web with Exa's index: a query instead of a url, for when you do not know where to look. Returns title, url and a snippet per result. To read the pages, pass the urls to web_scrape_batch. The engine is named because the price is Exa's, passed through with no markup and read from its own payment challenge on every call — today $0.007 per search.
| Name | Type | Req | Description |
|---|---|---|---|
| domains | array | – | Only these domains. |
| excludeDomains | array | – | Never these domains. |
| limit | number | – | Results (default 10, max 50). |
| query | string | yes | What to search for. |
| since | string | – | Only results published after this ISO date. |
| snippets | boolean | – | Text alongside each result (default true). |
No output schema declared.
No examples provided.
web_session_close ~45
Closes a session and stops billing browser time. Free. If you do not close it, it closes itself after a minute without use.
| Name | Type | Req | Description |
|---|---|---|---|
| sessionId | string | yes | – |
No output schema declared.
No examples provided.
web_session_open ~229
Opens a browser on a page and leaves it open, returning the map of controls. Use it when something has to be FILLED IN or CLICKED, not just read: inside the session the `controls` references keep working and you can act on the same state. $0.005 plus the outputs. Close it with web_session_close when you are done.
| Name | Type | Req | Description |
|---|---|---|---|
| formats | array | – | Outputs you want in the same response. `controls` is the map of what can be clicked; `elements` needs `selectors`; `json` needs `json.prompt`. |
| json | object | – | For the `json` format: `prompt` and/or `schema`. |
| maxAge | number | – | Accept an answer up to this many milliseconds old. A cache hit costs $0.0002 instead of the format price. Leave it out to force a fresh render. |
| selectors | array | – | CSS selectors for `elements`. |
| url | string | yes | Page to process. |
| wait | object | – | When to consider the page loaded: `until`, `selector`, `timeout`. |
No output schema declared.
No examples provided.
What is the oassis — web scraping, crawling and browser control for AI… MCP server?
oassis — web scraping, crawling and browser control for AI… is an MCP server listed in the public MCP registry as dev.oassis/scraper-crawler. Scrape to markdown, map and crawl sites, drive a real browser. Pay per call, no API key, no signup. This page covers its hosted endpoint (https://api.oassis.dev/mcp).
Is the oassis — web scraping, crawling and browser control for AI… MCP server safe to use?
oassis — web scraping, crawling and browser control for AI… scores 57 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the oassis — web scraping, crawling and browser control for AI… MCP server expose?
oassis — web scraping, crawling and browser control for AI… exposes 11 tools: web_scrape, web_session_open, web_act, web_scrape_batch, web_batch_status, and 6 more. Their descriptions and schemas cost roughly 1,921 tokens of context every time the server is loaded.
Does the oassis — web scraping, crawling and browser control for AI… MCP server require authentication?
No. We connected to oassis — web scraping, crawling and browser control for AI… without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the oassis — web scraping, crawling and browser control for AI… MCP server still maintained?
oassis — web scraping, crawling and browser control for AI… is still listed as active in the MCP registry. We last reached this channel on 1 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.